What IncarnaMind is
The project is described as an open-source way to chat with personal documents through large language models, using a sliding window chunking scheme and an ensemble retriever.
What you can do with it
- Ask questions across several PDF and TXT files at once
- Run simple and multi-hop queries over a document set
- Balance fine and coarse access with adaptive windows
Requirements and setup
- The GGUF version needs more than 35GB of GPU RAM
- Setup uses a Conda environment and installed dependencies
- An API key is placed in configparser.ini
Pros & cons
✓ What we like
- Multi-document chat removes the single-file limit
- Local open models are supported alongside hosted ones
! What to watch out for
- Running the GGUF version needs more than 35GB of GPU RAM
- Setup asks for an API key in configparser.ini
FAQ
Which file formats are supported?
The material lists PDF and TXT files.
Which models can it use?
It names OpenAI GPT, Anthropic Claude, Llama2 and other open LLMs.
Last reviewed: 2026-11-15
More AI chatbot tools
View all →-
360智脑 360 Brain AI assistant (China) Free tools Enterprise tools Chatbot Knowledge base Q&A Office -
A.(에이닷) SK Telecom's AI personal assistant Free tools Personal assistant Chatbot Search engine Office -
Agentz Omnichannel AI reception platform Enterprise tools Chatbot Knowledge base Q&A Customer service automation Lead generation -
AI Chat Multi-model chat aggregator Free tools Freemium tools Multi model platform Chatbot Knowledge base Q&A -
AI Front Desk AI phone receptionist for SMBs Free tools Personal assistant Privacy Chatbot Customer service automation -
AI Game Master DnD-style text adventure Free tools Freemium tools Chatbot